Expired60% confidenceFactTime unknown
For a 70-billion-parameter model (Sonnet scale) optimized through distillation and architectural improvements, the cost of generating 1,000 tokens in a single inference is approximately $0.003–$0.005.
1
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOn an NVIDIA H100 GPU, running a model of approximately 200 billion parameters (Opus scale), the cost of generating 1,000 tokens in a single inference is approximately $0.01–$0.03.78% similarUnverifiedThe price of Claude Sonnet 4.5 is exactly the same as the old version of Sonnet, allowing users to obtain performance at the $20–$100 tier that previously required the $200 tier.71% similarUnverifiedThe API cost of using Claude Sonnet 4.6 to analyze one coin photo is approximately $0.009.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/35037API
curl https://kongchang.com/api/v1/knowledge/claims/35037MCP
get_claim(id=35037)